Please use this identifier to cite or link to this item: https://bura.brunel.ac.uk/handle/2438/34194
Full metadata record
DC FieldValueLanguage
dc.contributor.authorGhorbani, Maziar-
dc.contributor.authorSuleimenova, Diana-
dc.contributor.authorHarbach, Laura-
dc.contributor.authorMazumdar, Pramit-
dc.contributor.authorParamanathan, Niruban-
dc.contributor.authorSeverino, Ricardo-
dc.contributor.authorAydemir, Özer-
dc.contributor.authorGroen, Derek-
dc.contributor.editorPaszynski, Maciej-
dc.contributor.editorBarnard, Amanda S-
dc.contributor.editorYongjie, Jessica Zhang-
dc.date.accessioned2026-11-17T18:46:06Z-
dc.date.available2026-11-17T18:46:06Z-
dc.date.issued2026-06-29-
dc.identifier.citationGhorbani, M. et al. (2026) 'Trustworthy Data Foundations for AI-Driven Analytics in Distributed IoT: A Validation-First Methodology', in M. Paszynski, A.S. Barnard and J.Z. Yongjie (eds.) Computational Science – ICCS 2026 Workshops (Lecture Notes in Computer Science, vol 16788). Cham: Springer Nature Switzerland, pp. 509–524. doi: 10.1007/978-3-032-29915-4_42.en_GB
dc.identifier.isbn9783032299147-
dc.identifier.isbn3032299152-
dc.identifier.issn0302-9743-
dc.identifier.urihttps://bura.brunel.ac.uk/handle/2438/34194-
dc.descriptionScript Availability:. To ensure reproducibility, the SQL script (ICCS-501-paper-metrics.sql) corresponding to queries Q1–Q8 and its accompanying reproduction guide (ICCS-501-paper-metrics-reproduction.md) have been formally committed to the HOMEPOT source repository (scripts directory). As HOMEPOT is an active industrial consortium project containing sensitive architectural infrastructure, full public release of the repository remains subject to cybersecurity clearance from our partners. However, the evaluation scripts and validation logic specifically accompanying this paper have been isolated to facilitate reproducibility: https://github.com/brunel-opensim/homepot-client.en_GB
dc.description.abstractReliable large language model (LLM)-assisted operations in distributed Internet of Things (IoT) systems depend fundamentally on the quality, structure, and provenance of telemetry available at inference time. In this paper, we present a validation-first methodology for AI-driven analytics that enforces end-to-end verification of the data pipeline before permitting LLM inference and retrieval-augmented generation. The approach formalises three pre-inference quality gates addressing infrastructure and schema conformance, data integrity across freshness and continuity constraints, and context readiness through deterministic, ID-bound prompt construction. This methodology is implemented in HOMEPOT (Homogeneous Cyber Management of End-Points and Operational Technology), a unified endpoint and IoT management platform supporting heterogeneous devices and MQTT-connected sensors. We conducted a 10-day Technology Readiness Level (TRL-4) pilot involving 10 devices, processing over 140,000 telemetry samples and health checks alongside continuous state-transition logging. Integrity indicators demonstrate 100% completeness for key telemetry fields and sub-minute maximum inter-arrival gaps, confirming strong temporal continuity. These results establish measurable readiness conditions under which AI inference is treated as a conditional capability rather than an assumed default, providing a reproducible blueprint for dependable AI integration in distributed IoT environments rapidly transitioning toward pilot-scale deployment.en_GB
dc.description.sponsorshipHOMEPOT (Homogeneous Cyber Management of End-Points and Operational Technology) project, an ITEA4-funded initiative supported by national funding agencies.en_GB
dc.format.extentpp. 509-524-
dc.format.mediumPrint-Electronic-
dc.languageEnglishen_GB
dc.language.isoenen_GB
dc.publisherSpringer Nature Switzerlanden_GB
dc.relation.ispartofseriesLecture Notes in Computer Science;LNCS 16788en_GB
dc.rightsRe-use licence for this version: InCopyright-
dc.rights.urihttps://rightsstatements.org/page/InC/1.0/-
dc.subjectvalidation-first methodologyen_GB
dc.subjectdistributed IoT systemsen_GB
dc.subjectdata quality assuranceen_GB
dc.subjectretrieval-augmented generationen_GB
dc.subjecttrustworthy AIen_GB
dc.subjecttelemetry integrityen_GB
dc.titleTrustworthy Data Foundations for AI-Driven Analytics in Distributed IoT: A Validation-First Methodologyen_GB
dc.typeBook chapteren_GB
dc.date.dateAccepted2026-03-23-
dc.identifier.doihttps://doi.org/10.1007/978-3-032-29915-4_42-
dc.relation.isPartOfLecture Notes in Computer Scienceen_GB
pubs.place-of-publicationCham-
pubs.publication-statusPublished-
pubs.volumeLNCS 16788-
dc.identifier.eissn1611-3349-
dcterms.dateAccepted2026-03-23-
dcterms.issued2026-
dcterms.issued2026-06-29-
dc.date.updated2026-11-17T18:36:29Z-
dc.contributor.orcidSuleimenova, Diana [0000-0003-4474-0943]-
dc.contributor.orcidGroen, Derek [0000-0001-7463-3765]-
dc.identifier.number42-
Appears in Collections:Department of Computer Science Embargoed Research Papers

Files in This Item:
File Description SizeFormat 
FullText.pdfEmbargoed until 29 June 2027. Copyright © 2026 The Author(s), under exclusive license to Springer Nature Switzerland AG. This is a pre-copyedited, author-produced version of a book chapter accepted for publication In: Paszynski, M., Barnard, A.S., Zhang, Y.J. (eds) Computational Science – ICCS 2026 Workshops. Lecture Notes in Computer Science, vol 16788, following peer review. The final authenticated version is available at https://doi.org/10.1007/978-3-032-29915-4_42 (see: https://www.springernature.com/gp/open-science/policies/book-policies).472.77 kBAdobe PDFView/Open


Items in BURA are protected by copyright, with all rights reserved, unless otherwise indicated.